1 December 2009 in IEEE Transactions on Pattern Analysis and Machine Intelligence
This paper considers feature selection for data classification in the presence of a huge number of irrelevant features. We propose a new feature-selection algorithm that addresses several major issues with prior work, including problems with algorithm implementation, computational complexity, and solution accuracy. The key idea is to decompose an arbitrarily complex nonlinear problem into a set of locally linear ones through local learning, and then learn feature relevance globally within the large margin framework. The proposed algorithm is based on well-established machine learning and numerical analysis techniques, without making any assumptions about the underlying data distribution. It is capable of processing many thousands of features within minutes on a personal computer while maintaining a very high accuracy that is nearly insensitive to a growing number of irrelevant features. Theoretical analyses of the algorithm's sample complexity suggest that the algorithm has a logarithmical sample complexity with respect to the number of features. Experiments on 11 synthetic and real-world data sets demonstrate the viability of our formulation of the feature-selection problem for supervised learning and the effectiveness of our algorithm.
7 August 2015 in IEEE Transactions on Pattern Analysis and Machine Intelligence
This paper addresses detection and localization of human activities in videos. We focus on activities that may have variable spatiotemporal arrangements of parts, and numbers of actors. Such activities are represented by a sum-product network (SPN). A product node in SPN represents a particular arrangement of parts, and a sum node represents alternative arrangements. The sums and products are hierarchically organized, and grounded onto space-time windows covering the video. The windows provide evidence about the activity classes based on the Counting Grid (CG) model of visual words. This evidence is propagated bottom-up and top-down to parse the SPN graph for the explanation of the video. The node connectivity and model parameters of SPN and CG are jointly learned under two settings, weakly supervised, and supervised. For evaluation, we use our new Volleyball dataset, along with the benchmark datasets VIRAT, UT-Interactions, KTH, and TRECVID MED 2011. Our video classification and activity localization are superior to those of the state of the art on these datasets.
10 August 2014 in International Journal of Computer Vision
2 February 2013 in International Journal of Computer Vision
17 December 2014 in Journal of Biomedical Semantics
Large quantities of digital images are now generated for biological collections, including those developed in projects premised on the high-throughput screening of genome-phenome experiments. These images often carry annotations on taxonomy and observable features, such as anatomical structures and phenotype variations often recorded in response to the environmental factors under which the organisms were sampled. At present, most of these annotations are described in free text, may involve limited use of non-standard vocabularies, and rarely specify precise coordinates of features on the image plane such that a computer vision algorithm could identify, extract and annotate them. Therefore, researchers and curators need a tool that can identify and demarcate features in an image plane and allow their annotation with semantically contextual ontology terms. Such a tool would generate data useful for inter and intra-specific comparison and encourage the integration of curation standards. In the future, quality annotated image segments may provide training data sets for developing machine learning applications for automated image annotation. We developed a novel image segmentation and annotation software application, “Annotation of Image Segments with Ontologies” (AISO). The tool enables researchers and curators to delineate portions of an image into multiple highlighted segments and annotate them with an ontology-based controlled vocabulary. AISO is a freely available Java-based desktop application and runs on multiple platforms. It can be downloaded at http://www.plantontology.org/software/AISO . AISO enables curators and researchers to annotate digital images with ontology terms in a manner which ensures the future computational value of the annotated images. We foresee uses for such data-encoded image annotations in biological data mining, machine learning, predictive annotation, semantic inference, and comparative analyses.